Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.6180. Min Act: -0.1700
Data Index: 2932114 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.3680. Min Act: -0.1700
Data Index: 7318053 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.3680. Min Act: -0.1700
Data Index: 4140911 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.3055. Min Act: -0.1698
Data Index: 3658592 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.3055. Min Act: -0.1700
Data Index: 2868750 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.2430. Min Act: -0.1700
Data Index: 1485937 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.2430. Min Act: -0.1700
Data Index: 5155942 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1805. Min Act: -0.1700
Data Index: 7009803 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1805. Min Act: -0.1700
Data Index: 3488110 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1805. Min Act: -0.1700
Data Index: 555115 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1805. Min Act: -0.1700
Data Index: 1981897 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1180. Min Act: -0.1700
Data Index: 7381143 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1180. Min Act: -0.1700
Data Index: 3656057 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1180. Min Act: -0.1700
Data Index: 1167630 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1180. Min Act: -0.1698
Data Index: 8269747 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1180. Min Act: -0.1700
Data Index: 7834844 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1805. Min Act: -0.1700
Data Index: 566984 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.1180. Min Act: -0.1700
Data Index: 3829723 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.0555. Min Act: -0.1700
Data Index: 3385037 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6180. Min Range: -10.6180
Max Act: 10.0555. Min Act: -0.1700
Data Index: 6756 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19